Applied Machine Learning fr ME

Catalog description

This course covers machine learning fundamentals, some popular and advanced machine learning models. Major topics include supervised learning (logistic regression, support vector machine, artificial neural networks, Gaussian process), unsupervised learning (clustering, dimensionality reduction), convolutional neural networks, generative adversarial networks, physics-constrained/informed neural networks, and optimization algorithms (stochastic gradient descent, Bayesian optimization). This course also covers the applications of machine learning models in mechanical engineering. Students should be familiar with Python basic commands and programming. Prerequisites: ME303 or equivalent. Offered in the Fall.